Merge pull request #66 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

.github/workflows/ci.yml

@@ -154,6 +154,39 @@ jobs:
         echo "region = BHS" >> $RCLONE_CONFIG_PATH
       if: github.event_name == 'push'
 
-    - name: Sync web
+    - name: Sync web with OVH
       run: rclone sync pandas_web ovh_cloud_pandas_web:dev
       if: github.event_name == 'push'
+
+    - name: Create git repo to upload the built docs to GitHub pages
+      run: |
+        cd pandas_web
+        git init
+        touch .nojekyll
+        echo "dev.pandas.io" > CNAME
+        printf "User-agent: *\nDisallow: /" > robots.txt
+        git add --all .
+        git config user.email "[email protected]"
+        git config user.name "pandas-bot"
+        git commit -m "pandas web and documentation in master"
+      if: github.event_name == 'push'
+
+    # For this task to work, next steps are required:
+    # 1. Generate a pair of private/public keys (i.e. `ssh-keygen -t rsa -b 4096 -C "[email protected]"`)
+    # 2. Go to https://github.com/pandas-dev/pandas/settings/secrets
+    # 3. Click on "Add a new secret"
+    # 4. Name: "github_pagas_ssh_key", Value: <Content of the private ssh key>
+    # 5. The public key needs to be upladed to https://github.com/pandas-dev/pandas-dev.github.io/settings/keys
+    - name: Install GitHub pages ssh deployment key
+      uses: shimataro/ssh-key-action@v2
+      with:
+        key: ${{ secrets.github_pages_ssh_key }}
+        known_hosts: 'github.com,192.30.252.128 ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAq2A7hRGmdnm9tUDbO9IDSwBK6TbQa+PXYPCPy6rbTrTtw7PHkccKrpp0yVhp5HdEIcKr6pLlVDBfOLX9QUsyCOV0wzfjIJNlGEYsdlLJizHhbn2mUjvSAHQqZETYP81eFzLQNnPHt4EVVUh7VfDESU84KezmD5QlWpXLmvU31/yMf+Se8xhHTvKSCZIFImWwoG6mbUoWf9nzpIoaSjB+weqqUUmpaaasXVal72J+UX2B+2RPW3RcT0eOzQgqlJL3RKrTJvdsjE3JEAvGq3lGHSZXy28G3skua2SmVi/w4yCE6gbODqnTWlg7+wC604ydGXA8VJiS5ap43JXiUFFAaQ=='
+      if: github.event_name == 'push'
+
+    - name: Publish web and docs to GitHub pages
+      run: |
+        cd pandas_web
+        git remote add origin [email protected]:pandas-dev/pandas-dev.github.io.git
+        git push -f origin master || true
+      if: github.event_name == 'push'

azure-pipelines.yml

@@ -15,78 +15,3 @@ jobs:
   parameters:
     name: Windows
     vmImage: vs2017-win2016
-
-- job: 'Web_and_Docs'
-  pool:
-    vmImage: ubuntu-16.04
-  timeoutInMinutes: 90
-  steps:
-  - script: |
-      echo '##vso[task.setvariable variable=ENV_FILE]environment.yml'
-      echo '##vso[task.prependpath]$(HOME)/miniconda3/bin'
-    displayName: 'Setting environment variables'
-
-  - script: |
-      sudo apt-get install -y libc6-dev-i386
-      ci/setup_env.sh
-    displayName: 'Setup environment and build pandas'
-
-  - script: |
-      source activate pandas-dev
-      python web/pandas_web.py web/pandas --target-path=web/build
-    displayName: 'Build website'
-
-  - script: |
-      source activate pandas-dev
-      # Next we should simply have `doc/make.py --warnings-are-errors`, everything else is required because the ipython directive doesn't fail the build on errors (https://github.com/ipython/ipython/issues/11547)
-      doc/make.py --warnings-are-errors | tee sphinx.log ; SPHINX_RET=${PIPESTATUS[0]}
-      grep -B1 "^<<<-------------------------------------------------------------------------$" sphinx.log ; IPY_RET=$(( $? != 1 ))
-      exit $(( $SPHINX_RET + $IPY_RET ))
-    displayName: 'Build documentation'
-
-  - script: |
-      mkdir -p to_deploy/docs
-      cp -r web/build/* to_deploy/
-      cp -r doc/build/html/* to_deploy/docs/
-    displayName: 'Merge website and docs'
-
-  - script: |
-      cd to_deploy
-      git init
-      touch .nojekyll
-      echo "dev.pandas.io" > CNAME
-      printf "User-agent: *\nDisallow: /" > robots.txt
-      git add --all .
-      git config user.email "[email protected]"
-      git config user.name "pandas-bot"
-      git commit -m "pandas web and documentation in master"
-    displayName: 'Create git repo for docs build'
-    condition : |
-      and(not(eq(variables['Build.Reason'], 'PullRequest')),
-          eq(variables['Build.SourceBranch'], 'refs/heads/master'))
-
-  # For `InstallSSHKey@0` to work, next steps are required:
-  # 1. Generate a pair of private/public keys (i.e. `ssh-keygen -t rsa -b 4096 -C "[email protected]"`)
-  # 2. Go to "Library > Secure files" in the Azure Pipelines dashboard: https://dev.azure.com/pandas-dev/pandas/_library?itemType=SecureFiles
-  # 3. Click on "+ Secure file"
-  # 4. Upload the private key (the name of the file must match with the specified in "sshKeySecureFile" input below, "pandas_docs_key")
-  # 5. Click on file name after it is created, tick the box "Authorize for use in all pipelines" and save
-  # 6. The public key specified in "sshPublicKey" is the pair of the uploaded private key, and needs to be set as a deploy key of the repo where the docs will be pushed (with write access): https://github.com/pandas-dev/pandas-dev.github.io/settings/keys
-  - task: InstallSSHKey@0
-    inputs:
-      hostName: 'github.com,192.30.252.128 ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAq2A7hRGmdnm9tUDbO9IDSwBK6TbQa+PXYPCPy6rbTrTtw7PHkccKrpp0yVhp5HdEIcKr6pLlVDBfOLX9QUsyCOV0wzfjIJNlGEYsdlLJizHhbn2mUjvSAHQqZETYP81eFzLQNnPHt4EVVUh7VfDESU84KezmD5QlWpXLmvU31/yMf+Se8xhHTvKSCZIFImWwoG6mbUoWf9nzpIoaSjB+weqqUUmpaaasXVal72J+UX2B+2RPW3RcT0eOzQgqlJL3RKrTJvdsjE3JEAvGq3lGHSZXy28G3skua2SmVi/w4yCE6gbODqnTWlg7+wC604ydGXA8VJiS5ap43JXiUFFAaQ=='
-      sshPublicKey: 'ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAACAQDHmz3l/EdqrgNxEUKkwDUuUcLv91unig03pYFGO/DMIgCmPdMG96zAgfnESd837Rm0wSSqylwSzkRJt5MV/TpFlcVifDLDQmUhqCeO8Z6dLl/oe35UKmyYICVwcvQTAaHNnYRpKC5IUlTh0JEtw9fGlnp1Ta7U1ENBLbKdpywczElhZu+hOQ892zqOj3CwA+U2329/d6cd7YnqIKoFN9DWT3kS5K6JE4IoBfQEVekIOs23bKjNLvPoOmi6CroAhu/K8j+NCWQjge5eJf2x/yTnIIP1PlEcXoHIr8io517posIx3TBup+CN8bNS1PpDW3jyD3ttl1uoBudjOQrobNnJeR6Rn67DRkG6IhSwr3BWj8alwUG5mTdZzwV5Pa9KZFdIiqX7NoDGg+itsR39QCn0thK8lGRNSR8KrWC1PSjecwelKBO7uQ7rnk/rkrZdBWR4oEA8YgNH8tirUw5WfOr5a0AIaJicKxGKNdMxZt+zmC+bS7F4YCOGIm9KHa43RrKhoGRhRf9fHHHKUPwFGqtWG4ykcUgoamDOURJyepesBAO3FiRE9rLU6ILbB3yEqqoekborHmAJD5vf7PWItW3Q/YQKuk3kkqRcKnexPyzyyq5lUgTi8CxxZdaASIOu294wjBhhdyHlXEkVTNJ9JKkj/obF+XiIIp0cBDsOXY9hDQ== [email protected]'
-      sshKeySecureFile: 'pandas_docs_key'
-    displayName: 'Install GitHub ssh deployment key'
-    condition : |
-      and(not(eq(variables['Build.Reason'], 'PullRequest')),
-          eq(variables['Build.SourceBranch'], 'refs/heads/master'))
-
-  - script: |
-      cd to_deploy
-      git remote add origin [email protected]:pandas-dev/pandas-dev.github.io.git
-      git push -f origin master
-    displayName: 'Publish web and docs to GitHub pages'
-    condition : |
-      and(not(eq(variables['Build.Reason'], 'PullRequest')),
-          eq(variables['Build.SourceBranch'], 'refs/heads/master'))

doc/source/getting_started/10min.rst

@@ -39,7 +39,7 @@ and labeled columns:
    df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
    df
 
-Creating a ``DataFrame`` by passing a dict of objects that can be converted to series-like.
+Creating a :class:`DataFrame` by passing a dict of objects that can be converted to series-like.
 
 .. ipython:: python
 
@@ -51,7 +51,7 @@ Creating a ``DataFrame`` by passing a dict of objects that can be converted to s
                        'F': 'foo'})
    df2
 
-The columns of the resulting ``DataFrame`` have different
+The columns of the resulting :class:`DataFrame` have different
 :ref:`dtypes <basics.dtypes>`.
 
 .. ipython:: python
@@ -169,7 +169,7 @@ See the indexing documentation :ref:`Indexing and Selecting Data <indexing>` and
 Getting
 ~~~~~~~
 
-Selecting a single column, which yields a ``Series``,
+Selecting a single column, which yields a :class:`Series`,
 equivalent to ``df.A``:
 
 .. ipython:: python
@@ -469,10 +469,10 @@ Concatenating pandas objects together with :func:`concat`:
    pd.concat(pieces)
 
 .. note::
-   Adding a column to a ``DataFrame`` is relatively fast. However, adding
+   Adding a column to a :class:`DataFrame` is relatively fast. However, adding
    a row requires a copy, and may be expensive. We recommend passing a
-   pre-built list of records to the ``DataFrame`` constructor instead
-   of building a ``DataFrame`` by iteratively appending records to it.
+   pre-built list of records to the :class:`DataFrame` constructor instead
+   of building a :class:`DataFrame` by iteratively appending records to it.
    See :ref:`Appending to dataframe <merging.concatenation>` for more.
 
 Join
@@ -520,15 +520,15 @@ See the :ref:`Grouping section <groupby>`.
                       'D': np.random.randn(8)})
    df
 
-Grouping and then applying the :meth:`~DataFrame.sum` function to the resulting
+Grouping and then applying the :meth:`~pandas.core.groupby.GroupBy.sum` function to the resulting
 groups.
 
 .. ipython:: python
 
    df.groupby('A').sum()
 
 Grouping by multiple columns forms a hierarchical index, and again we can
-apply the ``sum`` function.
+apply the :meth:`~pandas.core.groupby.GroupBy.sum` function.
 
 .. ipython:: python
 
@@ -648,7 +648,7 @@ the quarter end:
 Categoricals
 ------------
 
-pandas can include categorical data in a ``DataFrame``. For full docs, see the
+pandas can include categorical data in a :class:`DataFrame`. For full docs, see the
 :ref:`categorical introduction <categorical>` and the :ref:`API documentation <api.arrays.categorical>`.
 
 .. ipython:: python
@@ -664,14 +664,13 @@ Convert the raw grades to a categorical data type.
     df["grade"]
 
 Rename the categories to more meaningful names (assigning to
-``Series.cat.categories`` is inplace!).
+:meth:`Series.cat.categories` is inplace!).
 
 .. ipython:: python
 
     df["grade"].cat.categories = ["very good", "good", "very bad"]
 
-Reorder the categories and simultaneously add the missing categories (methods under ``Series
-.cat`` return a new ``Series`` by default).
+Reorder the categories and simultaneously add the missing categories (methods under :meth:`Series.cat` return a new :class:`Series` by default).
 
 .. ipython:: python
 

pandas/core/base.py

@@ -927,22 +927,50 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
 
     def argmax(self, axis=None, skipna=True, *args, **kwargs):
         """
-        Return an ndarray of the maximum argument indexer.
+        Return int position of the largest value in the Series.
+
+        If the maximum is achieved in multiple locations,
+        the first row position is returned.
 
         Parameters
         ----------
         axis : {None}
             Dummy argument for consistency with Series.
         skipna : bool, default True
+            Exclude NA/null values when showing the result.
+        *args, **kwargs
+            Additional arguments and keywords for compatibility with NumPy.
 
         Returns
         -------
-        numpy.ndarray
-            Indices of the maximum values.
+        int
+            Row position of the maximum values.
 
         See Also
         --------
-        numpy.ndarray.argmax
+        numpy.ndarray.argmax : Equivalent method for numpy arrays.
+        Series.argmin : Similar method, but returning the minimum.
+        Series.idxmax : Return index label of the maximum values.
+        Series.idxmin : Return index label of the minimum values.
+
+        Examples
+        --------
+        Consider dataset containing cereal calories
+
+        >>> s = pd.Series({'Corn Flakes': 100.0, 'Almond Delight': 110.0,
+        ...                'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0})
+        >>> s
+        Corn Flakes              100.0
+        Almond Delight           110.0
+        Cinnamon Toast Crunch    120.0
+        Cocoa Puff               110.0
+        dtype: float64
+
+        >>> s.argmax()
+        2
+
+        The maximum cereal calories is in the third element,
+        since series is zero-indexed.
         """
         nv.validate_minmax_axis(axis)
         nv.validate_argmax_with_skipna(skipna, args, kwargs)

pandas/core/frame.py

@@ -8446,9 +8446,8 @@ def isin(self, values) -> "DataFrame":
 
 def _from_nested_dict(data):
     # TODO: this should be seriously cythonized
-    new_data = {}
+    new_data = collections.defaultdict(dict)
     for index, s in data.items():
         for col, v in s.items():
-            new_data[col] = new_data.get(col, {})
             new_data[col][index] = v
     return new_data

pandas/core/indexes/base.py

@@ -796,20 +796,24 @@ def repeat(self, repeats, axis=None):
 
     def copy(self, name=None, deep=False, dtype=None, names=None):
         """
-        Make a copy of this object.  Name and dtype sets those attributes on
-        the new object.
+        Make a copy of this object.
+
+        Name and dtype sets those attributes on the new object.
 
         Parameters
         ----------
-        name : Label
+        name : Label, optional
+            Set name for new object.
         deep : bool, default False
         dtype : numpy dtype or pandas type, optional
+            Set dtype for new object.
         names : list-like, optional
             Kept for compatibility with MultiIndex. Should not be used.
 
         Returns
         -------
         Index
+            Index refer to new object which is a copy of this object.
 
         Notes
         -----
@@ -3933,18 +3937,35 @@ def memory_usage(self, deep: bool = False) -> int:
 
     def where(self, cond, other=None):
         """
-        Return an Index of same shape as self and whose corresponding
-        entries are from self where cond is True and otherwise are from
-        other.
+        Replace values where the condition is False.
+
+        The replacement is taken from other.
 
         Parameters
         ----------
         cond : bool array-like with the same length as self
-        other : scalar, or array-like
+            Condition to select the values on.
+        other : scalar, or array-like, default None
+            Replacement if the condition is False.
 
         Returns
         -------
-        Index
+        pandas.Index
+            A copy of self with values replaced from other
+            where the condition is False.
+
+        See Also
+        --------
+        Series.where : Same method for Series.
+        DataFrame.where : Same method for DataFrame.
+
+        Examples
+        --------
+        >>> idx = pd.Index(['car', 'bike', 'train', 'tractor'])
+        >>> idx
+        Index(['car', 'bike', 'train', 'tractor'], dtype='object')
+        >>> idx.where(idx.isin(['car', 'train']), 'other')
+        Index(['car', 'other', 'train', 'other'], dtype='object')
         """
         if other is None:
             other = self._na_value

pandas/core/indexing.py

@@ -8,7 +8,6 @@
 from pandas.util._decorators import Appender
 
 from pandas.core.dtypes.common import (
-    is_float,
     is_integer,
     is_iterator,
     is_list_like,
@@ -1500,18 +1499,10 @@ def _convert_to_indexer(self, key, axis: int, is_setter: bool = False):
         """
         Much simpler as we only have to deal with our valid types.
         """
-        labels = self.obj._get_axis(axis)
-
-        # make need to convert a float key
-        if isinstance(key, slice):
-            labels._validate_positional_slice(key)
-            return key
-
-        elif is_float(key):
-            # _validate_indexer call will always raise
-            labels._validate_indexer("positional", key, "iloc")
+        return key
 
-        self._validate_key(key, axis)
+    def _get_setitem_indexer(self, key):
+        # GH#32257 Fall through to let numnpy do validation
         return key
 
     # -------------------------------------------------------------------

pandas/tests/frame/indexing/test_indexing.py

@@ -27,6 +27,9 @@
 
 from pandas.tseries.offsets import BDay
 
+# We pass through a TypeError raised by numpy
+_slice_msg = "slice indices must be integers or None or have an __index__ method"
+
 
 class TestGet:
     def test_get(self, float_frame):
@@ -994,7 +997,8 @@ def test_getitem_setitem_fancy_exceptions(self, float_frame):
         with pytest.raises(IndexingError, match="Too many indexers"):
             ix[:, :, :]
 
-        with pytest.raises(IndexingError, match="Too many indexers"):
+        with pytest.raises(IndexError, match="too many indices for array"):
+            # GH#32257 we let numpy do validation, get their exception
             ix[:, :, :] = 1
 
     def test_getitem_setitem_boolean_misaligned(self, float_frame):
@@ -1073,7 +1077,7 @@ def test_getitem_setitem_float_labels(self):
 
         cp = df.copy()
 
-        with pytest.raises(TypeError, match=msg):
+        with pytest.raises(TypeError, match=_slice_msg):
             cp.iloc[1.0:5] = 0
 
         with pytest.raises(TypeError, match=msg):